def testSinglePreviousEvaluate(self): previousNeuron = InputNeuron() previousNeuron.setValue(1) previousRow = [previousNeuron] neuron = Neuron(previousRow) self.assertGreater(neuron.evaluate(), 1/2)
def testEvaluate(self): neuron = InputNeuron() neuronValue = random.randint(0,10) neuron.setValue(neuronValue) coefficient = random.randint(0,10) weightedNeuron = WeightedNeuron(neuron, coefficient) expectedValue = neuronValue * coefficient self.assertEqual(expectedValue, weightedNeuron.evaluate())
def __init__(self,
nbNeurons=5,
nbConnexions=5,
nbInputsNeurons=2,
nbOutputsNeurons=1,
genes=None):
self.fitness = 0.0
if (genes != None):
neuronGenes = genes[0]
connexionGenes = genes[1]
# print(neuronGenes)
# print(connexionGenes)
self.nbNeurons = 0
self.neuronList = []
self.inputNeuronList = []
self.outputNeuronList = []
self.connexionList = []
for neuronGene in neuronGenes:
neuron = None
if neuronGene[1] == 'n':
neuron = Neuron(self.nbNeurons, bias=neuronGene[0])
elif neuronGene[1] == 'i':
neuron = InputNeuron(self.nbNeurons, bias=neuronGene[0])
self.inputNeuronList.append(neuron)
elif neuronGene[1] == 'o':
neuron = OutputNeuron(self.nbNeurons, bias=neuronGene[0])
self.outputNeuronList.append(neuron)
self.neuronList.append(neuron)
self.nbNeurons += 1
for connGene in connexionGenes:
fromNeuron = self.neuronList[connGene[0]]
toNeuron = self.neuronList[connGene[1]]
self.connexionList.append(
Connexion(fromNeuron, toNeuron, connGene[2]))
self.nbConnexions = len(self.connexionList)
self.species = str(self.nbNeurons) + "_" + str(self.nbConnexions)
else:
self.nbNeurons = 0
self.neuronList = []
self.inputNeuronList = []
self.outputNeuronList = []
self.nbConnexions = 0
self.connexionList = []
self.species = str(self.nbNeurons) + "_" + str(self.nbConnexions)
for idInputNeuron in range(nbInputsNeurons):
self.createNeuron("input")
for idNeuron in range(nbNeurons - nbInputsNeurons -
nbOutputsNeurons):
self.createNeuron()
for idOutputNeuron in range(nbOutputsNeurons):
self.createNeuron("output")
for idConnexion in range(nbConnexions):
self.createConnexion()
self.clean()
def createNeuron(self, type="norm"):
if type == "input":
neuron = InputNeuron(self.nbNeurons)
self.neuronList.append(neuron)
self.inputNeuronList.append(neuron)
elif type == "output":
neuron = OutputNeuron(self.nbNeurons)
self.neuronList.append(neuron)
self.outputNeuronList.append(neuron)
else:
neuron = Neuron(self.nbNeurons)
self.neuronList.append(neuron)
self.nbNeurons += 1
def __init__(self, weightList, E, A, isBiasNeuronEnabled):
self.E = Decimal(E) #learning rate
self.A = Decimal(A) #momentum
self.inputs = []
self.outputs = []
self.idealOutput = []
self.isBiasNeuronEnabled = isBiasNeuronEnabled
# Creating input layer neurons
currentLayer = []
previousLayer = []
for i in range(len(weightList[0][0]) - int(isBiasNeuronEnabled)):
self.inputs.append(InputNeuron())
if isBiasNeuronEnabled:
self.inputs.append(BiasNeuron())
previousLayer = self.inputs
# Creating hidden layer neurons
for i in range(len(weightList) -
1): # -1 because start from second neuron layer
currentLayer = []
for j in range(len(
weightList[i])): # -1 because last check on bias neuron
neuron = HiddenNeuron()
currentLayer.append(neuron)
for k in range(len(weightList[i][j])):
self.__connect(Sinaps(Decimal(weightList[i][j][k])),
previousLayer[k], neuron)
if isBiasNeuronEnabled:
currentLayer.append(BiasNeuron())
previousLayer = currentLayer
# Creating output layer neurons
i = len(weightList) - 1
self.outputs = []
for j in range(len(weightList[i])):
neuron = OutputNeuron()
self.outputs.append(neuron)
for k in range(len(weightList[i][j])):
self.__connect(Sinaps(Decimal(weightList[i][j][k])),
previousLayer[k], neuron)
def _start_net(self):
#INICIA A REDE NEURAL COM OS PARAMETROS
#MONTANDo A REDE NO SENTINDO CONTRARIO
input = InputNeuron(self.NUMBER_INPUT_NEURONS)
self.input_layer = input
hidden = HiddenNeuron(self.NUMBER_HIDDEN_NEURONS, input)
self.hiddens_layers = []
self.hiddens_layers.append(hidden)
if (self.NUMBER_OF_LAYERS > 1):
for i in range(0, self.NUMBER_OF_LAYERS - 1):
hidden = HiddenNeuron(self.NUMBER_HIDDEN_NEURONS,
self.hiddens_layers[-1])
self.hiddens_layers.append(hidden)
output = OutputNeuron(self.NUMBER_OUTPUT_NEURONS,
self.hiddens_layers[-1])
self.output_layer = output
print("Created Input Layer:\t", self.NUMBER_INPUT_NEURONS)
print("Created Hidden Layer:\t", self.NUMBER_HIDDEN_NEURONS)
print("Created Output Layer:\t", self.NUMBER_OUTPUT_NEURONS)
def testInputNeuronValue(self): neuron = InputNeuron() expectedValue = random.randint(0,10) neuron.setValue(expectedValue) self.assertEqual(expectedValue, neuron.evaluate())
def testInputNeuronConstructor(self): neuron = InputNeuron() expectedValue = 0 self.assertEqual(expectedValue, neuron.evaluate())
